CN115146539A

CN115146539A - Vehicle safety evaluation parameter determination method and device and vehicle

Info

Publication number: CN115146539A
Application number: CN202210821601.3A
Authority: CN
Inventors: 谌杰
Original assignee: Xiaomi Automobile Technology Co Ltd
Current assignee: Xiaomi Automobile Technology Co Ltd
Priority date: 2022-07-12
Filing date: 2022-07-12
Publication date: 2022-10-04
Anticipated expiration: 2042-07-12
Also published as: CN115146539B

Abstract

The disclosure provides a method and a device for determining safety evaluation parameters of a vehicle and the vehicle, wherein the method comprises the following steps: determining a candidate risk value corresponding to each candidate object, wherein the candidate risk value describes a risk condition introduced by the candidate object to the vehicle, determining a target object from a plurality of candidate objects according to the candidate risk values, predicting whether a collision event occurs between the target object and the vehicle to obtain prediction result information, and generating a safety evaluation parameter corresponding to the prediction result information. By the method and the device, the safety state of each candidate object can be quantified based on the candidate risk value, so that the safety evaluation process is more pertinent, and more accurate safety evaluation parameters can be obtained.

Description

Vehicle safety evaluation parameter determination method and device and vehicle

Technical Field

The disclosure relates to the technical field of automatic driving, in particular to a method and a device for determining safety evaluation parameters of a vehicle and the vehicle.

Background

With the continuous definition of an automatic driving algorithm system and the continuous decoupling of the perception, decision and execution parts, the automatic driving decision algorithm is gradually mature. In order to reasonably evaluate the operation of the automated driving decision algorithm and the implementation of the decision scheme from a safety aspect, it is necessary to set appropriate evaluation criteria, especially when there is a risk but an accident has not occurred, i.e. under the condition of a near-accident event. Meanwhile, the evaluation criteria sensed according to the current vehicle running condition and the environmental information can be used as the basis for decision making of the automatic driving algorithm and fed back to the adjustment and iterative optimization of the decision making algorithm.

In the related art, the accuracy of the acquired security evaluation parameters is low.

Disclosure of Invention

The present disclosure is directed to solving, at least in part, one of the technical problems in the related art.

Therefore, the present disclosure aims to provide a method and an apparatus for determining a safety evaluation parameter of a vehicle, and a storage medium, which can quantify the safety state of each candidate object based on a candidate risk value, so that the safety evaluation process is more targeted, and more accurate safety evaluation parameters can be obtained.

The safety evaluation parameter determination method for the vehicle provided by the embodiment of the first aspect of the disclosure includes: determining a candidate risk value corresponding to each candidate object, wherein the candidate risk value describes a risk condition introduced by the candidate object to an own vehicle, determining a target object from a plurality of candidate objects according to the candidate risk value, predicting whether a collision event occurs between the target object and the own vehicle so as to obtain prediction result information, and generating a safety evaluation parameter corresponding to the prediction result information.

According to the method for determining the safety evaluation parameters of the vehicle, the candidate risk value corresponding to each candidate object is determined, wherein the candidate risk value describes the risk condition of the candidate object to the vehicle, the target object is determined from the candidate objects according to the candidate risk values, whether a collision event occurs between the target object and the vehicle is predicted, so that prediction result information is obtained, the safety evaluation parameters corresponding to the prediction result information are generated, the safety state of each candidate object can be quantified based on the candidate risk values, the safety evaluation process is more pertinent, and more accurate safety evaluation parameters can be obtained.

The safety evaluation parameter determination device for the vehicle provided by the embodiment of the second aspect of the disclosure comprises: the first determination module is used for determining a candidate risk value corresponding to each candidate object, wherein the candidate risk value describes a risk condition introduced by the candidate object to the vehicle; a second determining module, configured to determine a target object from the plurality of candidate objects according to the candidate risk value; the processing module is used for predicting whether a collision event occurs between the target object and the own vehicle to obtain prediction result information; and the survival module is used for generating a safety evaluation parameter corresponding to the prediction result information.

The vehicle safety evaluation parameter determination device provided by the embodiment of the second aspect of the disclosure determines the candidate risk value corresponding to each candidate object, wherein the candidate risk value describes a risk condition of the candidate object to the vehicle, determines the target object from the multiple candidate objects according to the candidate risk values, predicts whether a collision event occurs between the target object and the vehicle to obtain prediction result information, generates the safety evaluation parameter corresponding to the prediction result information, and can quantify the safety state of each candidate object based on the candidate risk value, so that the safety evaluation process is more pertinent, and more accurate safety evaluation parameters can be obtained.

A vehicle according to an embodiment of a third aspect of the present disclosure includes: the safety evaluation parameter determination method for the vehicle comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the safety evaluation parameter determination method for the vehicle according to the embodiment of the first aspect of the disclosure.

A fourth aspect of the present disclosure provides a non-transitory computer-readable storage medium, on which a computer program is stored, which when executed by a processor, implements a method for determining a safety evaluation parameter of a vehicle as set forth in the first aspect of the present disclosure.

A fifth aspect of the present disclosure provides a computer program product, wherein when instructions in the computer program product are executed by a processor, the method for determining safety evaluation parameters of a vehicle as set forth in the first aspect of the present disclosure is performed.

Additional aspects and advantages of the disclosure will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the disclosure.

Drawings

The foregoing and/or additional aspects and advantages of the present disclosure will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:

fig. 1 is a schematic flow chart of a method for determining safety evaluation parameters of a vehicle according to an embodiment of the present disclosure;

fig. 2 is a schematic flow chart of a method for determining safety evaluation parameters of a vehicle according to another embodiment of the present disclosure;

FIG. 3 is a schematic diagram of a sensing system for obtaining information according to an embodiment of the disclosure;

fig. 4 is a schematic flow chart of a method for determining safety evaluation parameters of a vehicle according to another embodiment of the present disclosure;

FIG. 5 is a schematic diagram illustrating the calculation of the sum of relative speeds and lateral distances in various directions according to the embodiment of the present disclosure;

FIG. 6 is a schematic view of a vehicle coordinate system in accordance with an embodiment of the present disclosure;

FIG. 7 is a schematic view of another vehicle coordinate system proposed by the embodiment of the present disclosure;

fig. 8 is a flowchart illustrating a method for determining a safety evaluation parameter of a vehicle according to another embodiment of the present disclosure;

FIG. 9 is a schematic diagram illustrating a collision duration calculation according to an embodiment of the present disclosure;

FIG. 10 is a schematic diagram illustrating a calculation of collision duration in a pursuit scenario according to an embodiment of the present disclosure;

FIG. 11 is a schematic diagram illustrating a late encroachment time acquisition as set forth in the embodiments of the present disclosure;

fig. 12 is a schematic diagram illustrating a security evaluation parameter obtaining process according to an embodiment of the disclosure;

fig. 13 is a schematic structural diagram of a safety evaluation parameter determination device for a vehicle according to an embodiment of the present disclosure;

fig. 14 is a schematic structural diagram of a safety evaluation parameter determination device for a vehicle according to another embodiment of the present disclosure;

fig. 15 is a schematic structural view of a vehicle according to an embodiment of the present disclosure;

FIG. 16 illustrates a block diagram of an exemplary electronic device suitable for use in implementing embodiments of the present disclosure.

Detailed Description

Reference will now be made in detail to the embodiments of the present disclosure, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the drawings are exemplary only for the purpose of illustrating the present disclosure and should not be construed as limiting the same. On the contrary, the embodiments of the disclosure include all changes, modifications and equivalents coming within the spirit and terms of the claims appended hereto.

Fig. 1 is a schematic flow chart of a method for determining a safety evaluation parameter of a vehicle according to an embodiment of the present disclosure.

It should be noted that, the subject of execution of the method for determining vehicle safety evaluation parameters in this embodiment is a vehicle safety evaluation parameter determining apparatus, which may be implemented in software and/or hardware, and the apparatus may be configured in an electronic device, which is a device that transmits data to or receives data from other devices via a communication facility, that is, the electronic device may be, for example, a smart phone, a smart watch, a portable computer, or the like, a vehicle-mounted device, which can perform network communication connection, and this is not limited.

As shown in fig. 1, the method for determining safety evaluation parameters of a vehicle includes:

s101: and determining a candidate risk value corresponding to each candidate object, wherein the candidate risk value describes the risk condition introduced by the candidate object to the vehicle.

The candidate objects refer to objects in a driving scene where the own vehicle is located, such as pedestrians, bicycles, automobiles, signboards, obstacles and the like.

The candidate risk value refers to a numerical value obtained by quantifying the risk condition of the candidate object introduced to the vehicle.

The self-vehicle may be a vehicle that executes the method for determining the safety evaluation parameter of the vehicle.

In some embodiments, when determining the candidate risk value corresponding to each candidate object, a method of artificial labeling may be adopted to evaluate the safety state of each candidate object in the driving scene for the vehicle based on the personal experience of the driver of the vehicle, so as to obtain the corresponding candidate risk value.

In other embodiments, when determining the candidate risk value corresponding to each candidate object, a third-party risk assessment device may be further used to assess the safety state of each candidate object in the driving scene with respect to the vehicle, so as to obtain the corresponding candidate risk value.

Of course, in some embodiments, the candidate risk value corresponding to each candidate object may be determined in any other possible manner, such as, without limitation, engineering or mathematical methods.

It is understood that a plurality of candidate objects may exist in the driving scene of the own vehicle, and when the candidate risk value corresponding to each candidate object is determined, the possible risks of the respective candidate objects to the own vehicle can be quantified, so that a reliable analysis basis is provided for the subsequent determination of the target object.

S102: and determining the target object from the candidate objects according to the candidate risk value.

The target object may be a candidate object whose corresponding candidate risk value satisfies a preset requirement.

In some embodiments, when determining the target object from the multiple candidate objects according to the candidate risk values, the obtaining number of the target objects may be configured in advance, for example, may be 3, the multiple candidate objects are sorted according to the size of the candidate risk values, and then the 3 candidate objects with the largest candidate risk values are selected as the target objects.

In other embodiments, when determining the target object from the multiple candidate objects according to the candidate risk values, attribute information (for example, volume, height, etc.) of the multiple candidate objects may also be obtained, and then the target object may be determined from the multiple candidate objects by combining the candidate risk values and the attribute information of the candidate objects.

Of course, in some embodiments, any other possible method may be adopted to determine the target object from the multiple candidate objects according to the candidate risk value, which is not limited in this respect.

In the embodiment of the disclosure, when the target object is determined from the plurality of candidate objects according to the candidate risk value, the target object meeting the preset requirement can be quickly screened out, so that the pertinence of the subsequent prediction process is effectively improved, and the resource utilization rate in the prediction process can be effectively improved.

S103: whether a collision event occurs between the target object and the own vehicle is predicted to obtain prediction result information.

The prediction result information is related information obtained by predicting whether a collision event occurs between the target object and the own vehicle by the execution subject according to the embodiment of the present disclosure. The prediction result information may be, for example, that a collision event has occurred between the target object and the own vehicle, or that no collision event has occurred between the target object and the own vehicle.

In some embodiments, when predicting whether a collision event occurs between the target object and the vehicle to obtain the prediction result information, the data simulation method may be adopted to respectively predict the motion trajectory curves corresponding to the target object and the vehicle in a future period, and then the prediction result information may be obtained according to the motion trajectory curves of the two vehicles.

In other embodiments, when predicting whether a collision event occurs between the target object and the vehicle to obtain the prediction result information, a communication link between the execution main body and the big data server in the embodiment of the present disclosure may be established in advance, and then the big data server predicts whether a collision event occurs between the target object and the vehicle to obtain the prediction result information, and transmits the prediction result information to the execution main body in the embodiment of the present disclosure, which is not limited thereto.

Of course, in some embodiments, any other possible method may also be used to predict whether a collision event occurs between the target object and the own vehicle, so as to obtain the prediction result information, which is not limited herein.

In the embodiment of the disclosure, when whether a collision event occurs between the target object and the vehicle is predicted to obtain the prediction result information, a reliable reference basis can be provided for subsequently generating the safety evaluation parameter.

S104: and generating a safety evaluation parameter corresponding to the prediction result information.

The safety evaluation parameter is a numerical value generated by quantifying the safety state of the vehicle based on the prediction result information.

It can be understood that, with the rapid development of the automatic driving technology, the safety during the automatic driving process is valued by many users, and the safety evaluation parameters obtained in the embodiment of the disclosure can accurately and clearly describe the current safety state of the vehicle, so that a reliable reference basis can be provided for the performance evaluation of the automatic driving algorithm.

In this embodiment, a candidate risk value corresponding to each candidate object is determined, where the candidate risk value describes a risk condition introduced by the candidate object to the own vehicle, a target object is determined from a plurality of candidate objects according to the candidate risk value, whether a collision event occurs between the target object and the own vehicle is predicted, so as to obtain prediction result information, and a safety evaluation parameter corresponding to the prediction result information is generated.

Fig. 2 is a schematic flowchart of a method for determining safety evaluation parameters of a vehicle according to another embodiment of the disclosure.

As shown in fig. 2, the method for determining the safety evaluation parameter of the vehicle includes:

s201: a candidate type for each candidate object is determined.

The candidate type may refer to a type of a candidate object.

For example, in the embodiment of the present disclosure, a sensing system may be configured in advance in an execution subject of the embodiment of the present disclosure, and the sensing system divides a plurality of candidate objects into a plurality of types, such as motor vehicles, non-motor vehicles, pedestrians, obstacles, and the like.

S202: and determining a candidate risk value corresponding to each candidate object according to the candidate type.

In the embodiment of the present disclosure, when determining the candidate risk value corresponding to each candidate object according to the candidate type, the candidate risk value corresponding to each candidate object may be determined based on a relationship table, where the candidate risk value corresponding to the candidate type may be configured in the relationship table in advance, or attribute information (such as volume, speed, and the like) of the candidate object may also be obtained, and the candidate risk value corresponding to each candidate object is determined based on the candidate type and the attribute information, which is not limited to this.

That is to say, in the embodiment of the present disclosure, the candidate type of each candidate object may be determined, and the candidate risk value corresponding to each candidate object may be determined according to the candidate type, because the candidate objects of the same type have higher similarity to the risk brought by the vehicle, when the candidate risk value corresponding to each candidate object is determined according to the candidate type, the accuracy of the obtained candidate risk value may be effectively improved while the candidate risk value corresponding to each candidate object is rapidly determined.

S203: and selecting a candidate object corresponding to the candidate risk value larger than the risk threshold value from the plurality of candidate objects as a target object.

The risk threshold may be a threshold value configured for the candidate risk value in advance.

That is to say, in the embodiment of the present disclosure, after determining the candidate risk value corresponding to each candidate object according to the candidate type, the candidate object corresponding to the candidate risk value greater than the risk threshold may be selected from the multiple candidate objects as the target object, so that the multiple candidate objects may be screened based on the risk threshold, the candidate object having the candidate risk value greater than the risk threshold is used as the target object to predict the collision event, and the candidate object having the candidate risk value less than or equal to the risk threshold may be effectively prevented from bringing the calculation cost to the collision event prediction process.

S204: and acquiring target positioning information, a target speed vector and a target acceleration vector of the target object.

In the embodiment of the disclosure, a world coordinate system may be established on a running plane of a host vehicle, wherein an origin of coordinates may be selected at any position. In the world coordinate system, the coordinates of the target object may be used as target positioning information. The velocity vector of the target object, which may be used as the target velocity vector, describes the magnitude and direction of the velocity of the target object in the world coordinate system. The acceleration vector of the target object, i.e., the acceleration vector that can be used as the target acceleration vector, is used to describe the magnitude and direction of the acceleration of the target object. It will be appreciated that the target velocity vector and the target acceleration vector of the target object may be in different directions.

S205: the method comprises the steps of obtaining the self-vehicle positioning information, the self-vehicle speed vector and the self-vehicle acceleration vector of a self-vehicle.

The coordinates of the vehicle in the world coordinate system can be used as the vehicle positioning information, the speed vector can be used as the vehicle speed vector, and the acceleration vector can be used as the vehicle acceleration vector.

For example, a sensing system may be configured in advance in an execution subject of the embodiment of the disclosure to obtain information related to a vehicle and a target object, as shown in fig. 3, fig. 3 is a schematic diagram of information obtained by the sensing system provided in the embodiment of the disclosure, and in a near-accident event, that is, when no collision or other event occurs at the current time, positioning information, such as a positioning coordinate (x) of a vehicle (for short, a vehicle) may be obtained by the sensing system according to each time frame (an operation time unit of an automatic driving algorithm), where the positioning information is obtained by the sensing system ₀ ,y ₀ ,z ₀ ) Velocity vector (v) _0,x ,v _0,y ,v _0,z ) Acceleration vector (a) _0,x ,a _0,y ,a _0,z ) Location coordinates (x) of target objects (e.g., target 1 and target 2) ₁ ,y ₁ ,z ₁ ) And (x) ₂ ,y ₂ ,z ₂ ) Velocity vector (v) _1,x ,v _1,y ,v _1,z ) And (v) _2,x ,v _2,y ,v _2,z ) Acceleration vector (a) _1,x ,a _1,y ,a _1,z ) And (a) _2,x ,a _2,y ,a _2,z )。

In the embodiment of the disclosure, traffic participants (i.e., the own vehicle and the target object) can be abstracted into particles, and the shape and the geometric size of the particles are ignored, so that the calculation process is simplified, and the calculation burden of the control unit is reduced.

S206: and determining a plurality of target position points respectively corresponding to the plurality of predicted time points according to the target positioning information, the target velocity vector and the target acceleration vector.

The predicted time point may be a time point after the current time point, and the number of the predicted time points may be plural. For example, a predicted time point may be selected every 3 seconds after the current time point.

The target location point may be a coordinate point corresponding to the target object at the predicted time point.

In the embodiment of the disclosure, when a plurality of target position points corresponding to a plurality of prediction time points are determined according to the target positioning information, the target velocity vector, and the target acceleration vector, the coordinate position information of the target object within a period of time can be accurately predicted, so that reliable reference data can be provided for the prediction process.

S207: and determining a plurality of vehicle position points respectively corresponding to the plurality of predicted time points according to the vehicle positioning information, the vehicle speed vector and the vehicle acceleration vector.

The vehicle position point refers to a coordinate position of the vehicle corresponding to the predicted time point.

In the embodiment of the present disclosure, when a plurality of vehicle location points respectively corresponding to a plurality of predicted time points are determined according to the vehicle positioning information, the vehicle velocity vector, and the vehicle acceleration vector, the obtained vehicle location points may be analyzed to correspond to the target location point to generate corresponding predicted result information.

S208: a plurality of distance values corresponding to the plurality of predicted time points are determined, wherein the distance values describe distances between the target position point and the vehicle position point at the corresponding predicted time points.

The distance value refers to a relative distance between the target position point and the vehicle position point at the predicted time point. It is understood that, when determining a plurality of distance values corresponding to a plurality of predicted time points, respectively, the resulting plurality of distance values may accurately describe the relative distance of the own vehicle to the target object at each predicted time point, thereby providing reliable reference data for subsequent determination of the prediction result information.

S209: and determining the prediction result information according to the plurality of distance values.

In some embodiments, when determining the prediction result information based on a plurality of distance values, it may be that a distance variation tendency between the own vehicle and the target object is predicted based on the plurality of distance values, and when the distance between the own vehicle and the target object tends to be stable or tends to be large, it is determined that the collision event is not predicted, and when the distance between the own vehicle and the target object tends to be small, it is determined that the collision event is predicted.

In other embodiments, when determining the prediction result information according to a plurality of distance values, the plurality of distance values may be input into a pre-trained machine learning model to obtain corresponding prediction result information.

Of course, any other possible method may be used to determine the prediction result information according to the plurality of distance values, such as engineering or a combination of figures and shapes, which is not limited herein.

Optionally, in some embodiments, when determining the prediction result information according to the plurality of distance values, it may be determined that the prediction result information is a predicted collision event when the distance value corresponding to at least one prediction time point is less than or equal to the distance threshold, and it may be determined that the prediction result information is a predicted non-collision event when the distance value corresponding to any one prediction time point is greater than the distance threshold, so that whether a collision event occurs between the host vehicle and the target object may be accurately predicted based on a comparison result between the distance threshold and the plurality of distance values, and the practicability of the prediction process may be effectively improved.

The distance threshold may be a threshold configured in advance for the distance value.

By way of example, the computational pseudo-code of the prediction result information, i.e., whether there is a risk of collision (Near Miss), may be expressed as:

"danger of collision = NearMiss (own vehicle positioning coordinate, target positioning coordinate, own vehicle velocity vector, target velocity vector, own vehicle acceleration vector, target acceleration vector, number of calculation time frames)

{

Calculating the coordinates of the vehicle under each time frame;

calculating target coordinates under each time frame;

enumerating each time frame:

{

if (the distance between the coordinates of the own vehicle and the target coordinates in the current time frame is less than a threshold value):

there is a risk of collision;

else：

there is no risk of collision;

}”

inputting data:

the own vehicle location coordinates ([ x _0, y _0, z _0 ]): and positioning coordinates of the vehicle.

Target positioning coordinates ([ x _ i, y _ i, z _ i ]): the location coordinates of the target object.

Own vehicle velocity vector (V _0= [ V _ (0, x), V _ (0, y), V _ (0, z) ]): the speed and direction of the vehicle.

Target velocity vector (V _ i = [ V _ (i, x), V _ (i, y), V _ (i, z) ]): the magnitude and direction of the velocity of the target object.

Own vehicle acceleration vector (a _0= [ a _ (0, x), a _ (0, y), a _ (0, z) ]): the magnitude and direction of acceleration of the vehicle.

Target acceleration vector (a _ i = [ a _ (i, x), a _ (i, y), a _ (i, z) ]): magnitude and direction of acceleration of the target object.

Outputting data:

collision risk: semaphore (0/1) whether collision is possible.

For example, when t =0, the location coordinate of the host vehicle is ([ x ]) ₀ ,y ₀ ,z ₀ ]) The velocity vector of the bicycle is V ₀ ＝[V _0,x ,V _0,y ,V _0,z ]Acceleration vector of the vehicle is a ₀ ＝[a _0,x ,a _0,y ,a _0,z ]Then, thenAt t = t _i And then, the coordinates of the corresponding self-vehicle position points of the self-vehicle are as follows:

wherein i Δ t is t =0 to t = t _i The time difference between them.

That is, after selecting a candidate object corresponding to a candidate risk value greater than a risk threshold value from a plurality of candidate objects as a target object, the embodiments of the present disclosure may obtain target positioning information, a target velocity vector, and a target acceleration vector of the target object, obtain self-vehicle positioning information, a self-vehicle velocity vector, and a self-vehicle acceleration vector of a self-vehicle, determine a plurality of target location points corresponding to a plurality of predicted time points, respectively, from the target positioning information, the target velocity vector, and the target acceleration vector, determine a plurality of self-vehicle location points corresponding to a plurality of predicted time points, respectively, from the self-vehicle positioning information, the self-vehicle velocity vector, and the self-vehicle acceleration vector, determine a plurality of distance values corresponding to a plurality of predicted time points, respectively, wherein the distance values describe distances between the target location points and the self-vehicle location points at the corresponding predicted time points, determine prediction result information according to the plurality of distance values, thereby accurately predicting distance values between the target object and the self-vehicle at the plurality of predicted time points based on related information such as positioning information, velocity vector, acceleration vector, and the obtained distance values may represent effective distances between the self-vehicle and the target object, thereby may improve reliability of the obtained prediction information of the self-vehicle.

S210: and generating a safety evaluation parameter corresponding to the prediction result information.

For the description of S210, reference may be made to the foregoing embodiments, which are not described herein again.

In the embodiment, the candidate type of each candidate object is determined, and the candidate risk value corresponding to each candidate object is determined according to the candidate type, so that the candidate risk value corresponding to each candidate object can be determined quickly and the accuracy of the obtained candidate risk value can be improved effectively when the candidate risk value corresponding to each candidate object is determined according to the candidate type because the candidate objects of the same type have higher similarity to the risk brought by the vehicle. The candidate object corresponding to the candidate risk value larger than the risk threshold is selected from the candidate objects to serve as the target object, therefore, the candidate objects can be screened based on the risk threshold, the candidate object with the candidate risk value larger than the risk threshold is used as the target object to predict the collision event, and the candidate object with the candidate risk value smaller than or equal to the risk threshold can be effectively prevented from bringing calculation cost to the collision event prediction process. The method comprises the steps of obtaining target positioning information, a target speed vector and a target acceleration vector of a target object, obtaining self-positioning information, a self-speed vector and a self-acceleration vector of a self-vehicle, determining a plurality of target position points corresponding to a plurality of prediction time points according to the target positioning information, the target speed vector and the target acceleration vector, determining a plurality of self-position points corresponding to the prediction time points according to the self-positioning information, the self-speed vector and the self-acceleration vector, determining a plurality of distance values corresponding to the prediction time points respectively, wherein the distance values describe distances between the target position points and the self-position points at the corresponding prediction time points, and determining prediction result information according to the distance values, so that the distance values of the target object and the self-vehicle at the prediction time points can be accurately predicted based on relevant information such as the positioning information, the speed vector and the acceleration vector, and the obtained distance can represent the relative distance between the self-vehicle and the target object effectively, and the reliability of the obtained prediction result information can be effectively improved. When the distance value corresponding to at least one prediction time point is smaller than or equal to the distance threshold value, the prediction result information is determined to predict the occurrence of the collision event, and when the distance value corresponding to any prediction time point is larger than the distance threshold value, the prediction result information is determined to predict the non-occurrence of the collision event, so that whether the collision event occurs between the own vehicle and the target object can be accurately predicted based on the comparison result of the distance threshold value and a plurality of distance values, and the practicability of the prediction process can be effectively improved.

Fig. 4 is a schematic flow chart of a method for determining safety evaluation parameters of a vehicle according to another embodiment of the present disclosure.

As shown in fig. 4, the method for determining the safety evaluation parameter of the vehicle includes:

s401: a candidate type for each candidate object is determined.

For the description of S401, reference may be made to the foregoing embodiments, which are not described herein again.

S402: a risk weight factor corresponding to the candidate type is obtained.

The risk weight factor may be a scaling factor that is determined for each candidate type and is different according to the relative risk degree of each candidate type to the vehicle.

For example, the candidate type may be pedestrian, bicycle, motorcycle, automobile, and the risk weight factor may be taken as: pedestrian > bicycle > motorcycle > car.

S403: and acquiring candidate positioning information and a candidate speed vector of the candidate object, and acquiring the self-vehicle positioning information and the self-vehicle speed vector of the self-vehicle.

Wherein, the coordinates and the velocity vector corresponding to the candidate object in the world coordinate system can be used as the candidate positioning information and the candidate velocity vector, respectively.

S404: and processing the candidate positioning information, the candidate speed vector, the self-vehicle positioning information and the self-vehicle speed vector according to the risk weight factor to obtain a candidate risk value.

In some embodiments, when the candidate positioning information, the candidate velocity vector, the vehicle positioning information, and the vehicle velocity vector are processed according to the risk weight factor to obtain the candidate risk value, the candidate positioning information, the candidate velocity vector, the vehicle positioning information, and the vehicle velocity vector may be input into a pre-trained risk assessment model to obtain a reference risk value, and then the reference risk value is processed according to the risk weight factor to obtain the candidate risk value.

In other embodiments, when the candidate positioning information, the candidate velocity vector, the vehicle positioning information, and the vehicle velocity vector are processed according to the risk weight factor to obtain the candidate risk value, a corresponding motion trajectory diagram may be generated based on the candidate positioning information, the candidate velocity vector, the vehicle positioning information, and the vehicle velocity vector by using a number-form combination method, and then the motion trajectory diagram is labeled and processed based on the risk weight factor to obtain the candidate risk value.

Of course, in some embodiments, any other possible method may be adopted to process the candidate location information, the candidate velocity vector, the own location information, and the own velocity vector according to the risk weight factor to obtain the candidate risk value, which is not limited in this regard.

Alternatively, in some embodiments, when the candidate location information, the candidate speed vector, the self-vehicle location information, and the self-vehicle speed vector are processed according to the risk weighting factors to obtain the candidate risk value, a first risk factor introduced by a lateral distance between the candidate object and the self-vehicle may be determined according to the candidate location information and the self-vehicle location information, a second risk factor introduced by a relative speed between the candidate object and the self-vehicle may be determined according to the candidate speed vector and the self-vehicle speed vector, and the first risk factor and the second risk factor may be processed according to the risk weighting factors to obtain the candidate risk value, where the first risk factor and the second risk factor may accurately describe risk information introduced by the candidate object to the self-vehicle in different dimensions, and when the first risk factor and the second risk factor are processed based on the risk weighting factors, attribute information of the candidate object may be effectively combined, so that adaptability between the obtained candidate risk value and the driving scene may be effectively improved.

The first risk factor may refer to a risk value introduced by a lateral distance between the candidate object and the own vehicle to the own vehicle. And the second risk factor may refer to a risk value that a relative speed between the candidate object and the own vehicle introduces to the own vehicle.

For example, the candidate risk value may be a Speed Distance alarm (SDC) describing a risk factor introduced by the sum of the directional relative speeds of the vehicle and the candidate object and the lateral Distance. When the sum of the relative speeds of the host vehicle and the candidate object in all directions is larger or the transverse distance is smaller, there is generally a greater risk that the calculation should be prioritized in the subsequent safety evaluation parameters.

The computational pseudo-code of the speed distance alarm can be expressed as:

"speed distance alarm = SDC (location information, candidate type, speed vector of the vehicle, candidate speed vector)

{

The transverse distance = the projection length of the distance between the two vehicles in the Y direction under the coordinate system of the vehicle;

the sum of the relative speeds in each direction = Σ (| difference |) of the components of the two vehicle speed vectors in the world coordinate system;

calculating speed and distance alarm according to the candidate types;

}”

inputting data:

location coordinates ([ x ]) of bicycle ₀ ,y ₀ ,z ₀ ]): and positioning coordinates of the vehicle.

Candidate location coordinates ([ x ] _i ,y _i ,z _i ]): location coordinates of the candidate object.

Velocity vector (V) of bicycle ₀ ＝[V _0,x ,V _0,y ,V _0,z ]): the speed and direction of the vehicle.

Candidate velocity vector (V) _i ＝[V _i,x ,V _i,y ,V _i,z ]): the velocity magnitude and direction of the candidate.

Outputting data:

and (4) speed and distance alarming: and the risk factor jointly introduced by the sum of the relative speeds of the self-vehicle and the target in all directions and the transverse distance is the candidate risk value.

For example, as shown in fig. 5, fig. 5 is a schematic diagram illustrating the calculation of the sum of relative speeds in each direction and the lateral distance, where the sum S of relative speeds in each direction is defined as the sum of absolute values of differences between speed components of the host vehicle and the candidate object in the world coordinate system, that is:

S＝|V _i，x -V _0，x |+|V _i，y -V _0，y |+|V _i，z -V _0，z |；

where i refers to the number of the candidate, e.g. candidate 1 corresponds to i =1,v _i,x I.e. the velocity vector V of the candidate i _i Component above the x-axis, V _i,y I.e. the velocity vector V of the candidate i _i Component above the y-axis, V _i,z I.e. the velocity vector V of the candidate i _i The component above the z-axis.

And V _0,x I.e. velocity vector V of the own vehicle ₀ Component above the x-axis, V _0,y I.e. velocity vector V of the own vehicle ₀ Component above the y-axis, V _0,z I.e. velocity vector V of the own vehicle ₀ The component above the z-axis.

The lateral distance may be defined as a projection of a distance between the vehicle and the candidate object on a Y-axis of a vehicle coordinate system. The Y-axis direction of the vehicle coordinate system is not considered under the condition of vehicle geometric shape

Namely, the Z-axis component of the world coordinate system is zero, and the velocity vector normal vector positioned on the left side of the vehicle velocity direction is calculated in the following way:

for example, as shown in fig. 6 and 7, fig. 6 is a schematic view of a vehicle coordinate system according to an embodiment of the disclosure, and fig. 7 is a schematic view of another vehicle coordinate system according to an embodiment of the disclosure, where in fig. 6, a vector b61 is a velocity vector, and a vector b62 is [ V ] _0,x ,V _0,y ,0]That is, in the X-axis direction of the vehicle coordinate system, corresponding to the condition that the component of the velocity vector b61 in the z-axis direction of the vehicle coordinate system is not zero, the vector b72 in FIG. 7 is the auxiliary calculation vector [0, -1 ]]When the z-axis component of the velocity vector b71 in the vehicle coordinate system is zero, the direction of the velocity vector b71 is the X-axis direction of the vehicle coordinate system, and the vector b73 is calculatedThe vehicle coordinate system is a unit vector in the Y-axis direction.

The lateral distance D is then:

accordingly, the risk weighting factor w corresponding to the candidate type can be obtained _D And w _S The speed distance alarm SDC is calculated as follows:

wherein, w _D And w _S For the weight factors determined on the basis of the type of candidate, each type of candidate, e.g. pedestrian, bicycle, motorcycle, automobile, corresponding to a set w _D And w _S . Typically, in determining the weight factor, the pedestrian is taken>Bicycle with a steering wheel>Motorcycle with a motorcycle body>An automobile.

After the SDC of the surrounding objects is calculated, all the objects can be sorted from large SDC to small SDC, and if the SDC is large, the risk is high, and the SDC should be considered preferentially in the subsequent calculation process.

In the embodiment of the present disclosure, a computer program may be configured in advance for processing the candidate positioning information, the candidate velocity vector, the own positioning information, and the own velocity vector according to the risk weight factor to obtain the candidate risk value.

That is, after determining the candidate type of each candidate object, the embodiments of the present disclosure may acquire a risk weight factor corresponding to the candidate type, acquire candidate positioning information and a candidate speed vector of the candidate object, and acquire own positioning information and an own speed vector of the own vehicle, process the candidate positioning information, the candidate speed vector, the own positioning information, and the own speed vector according to the risk weight factor to obtain a candidate risk value, and thereby, may effectively combine the positioning information and the speed vector of the candidate object and the own vehicle in the driving scene, thereby effectively improving the description accuracy of the obtained candidate risk value for the candidate object risk value in the driving scene.

S405: and determining the target object from the candidate objects according to the candidate risk value.

S406: whether a collision event occurs between the target object and the own vehicle is predicted to obtain prediction result information.

For description of S405 and S406, reference may be made to the above embodiments, which are not described herein again.

S407: a first safety evaluation parameter corresponding to the predicted crash event is generated.

The first safety evaluation parameter refers to a safety evaluation parameter corresponding to the predicted collision event. The first safety evaluation parameter may be used to evaluate a safety status of the host vehicle in the event of a collision.

In the embodiment of the present disclosure, when generating the first safety evaluation parameter corresponding to the predicted collision event, the motion trajectory of the vehicle and the target object may be obtained, and the maximum distance value of the joint portion of the motion trajectory is determined as the first safety evaluation parameter, or the third-party safety evaluation device may be further used to perform safety evaluation on the vehicle in the driving scene to obtain the first safety evaluation parameter, and transmit the first safety evaluation parameter to the execution main body of the embodiment of the present disclosure, which is not limited thereto.

S408: a second safety evaluation parameter corresponding to the predicted non-occurrence of the collision event is generated.

The second safety evaluation parameter is a safety evaluation parameter corresponding to the predicted non-occurrence of the collision event. The second safety evaluation parameter may be used to evaluate the safety state of the own vehicle when no collision event occurs.

In the embodiment of the present disclosure, when generating the second safety evaluation parameter corresponding to the predicted non-occurrence of the collision event, a minimum value of the plurality of distance values may be acquired as the second safety evaluation parameter, or a maximum relative acceleration vector between the target object and the own vehicle may be acquired as the second safety evaluation parameter, which is not limited thereto.

That is, in the embodiment of the present disclosure, after predicting whether a collision event occurs between the target object and the vehicle to obtain the prediction result information, the first safety evaluation parameter corresponding to the predicted collision event may be generated, or the second safety evaluation parameter corresponding to the predicted non-collision event may be generated, so that the obtained safety evaluation parameter may be adapted to the personalized prediction result information, and the comprehensiveness of the obtained safety evaluation parameter may be effectively improved.

In the embodiment, the candidate positioning information and the candidate speed vector of the candidate object are obtained by obtaining the risk weight factor corresponding to the candidate type, the self-vehicle positioning information and the self-vehicle speed vector of the self-vehicle are obtained, and the candidate positioning information, the candidate speed vector, the self-vehicle positioning information and the self-vehicle speed vector are processed according to the risk weight factor to obtain the candidate risk value. The method comprises the steps of determining a first risk factor introduced by the transverse distance between a candidate object and a vehicle according to candidate positioning information and the vehicle positioning information, determining a second risk factor introduced by the relative speed between the candidate object and the vehicle according to a candidate speed vector and the vehicle speed vector, processing the first risk factor and the second risk factor according to risk weight factors to obtain a candidate risk value, wherein the first risk factor and the second risk factor can accurately describe the risk information introduced by the candidate object to the vehicle in different dimensions, and when the first risk factor and the second risk factor are processed based on the risk weight factors, the attribute information of the candidate object can be effectively combined, so that the adaptability between the obtained candidate risk value and a driving scene is effectively improved. By generating the first safety evaluation parameter corresponding to the predicted collision event or generating the second safety evaluation parameter corresponding to the predicted non-collision event, the obtained safety evaluation parameter can be adapted to the individualized prediction result information, and the comprehensiveness of the obtained safety evaluation parameter can be effectively improved.

Fig. 8 is a schematic flowchart of a method for determining safety evaluation parameters of a vehicle according to another embodiment of the disclosure.

As shown in fig. 8, the method for determining the safety evaluation parameter of the vehicle includes:

s801: and determining a candidate risk value corresponding to each candidate object, wherein the candidate risk value describes the risk condition introduced by the candidate object to the vehicle.

S802: and determining the target object from the candidate objects according to the candidate risk value.

S803: whether a collision event occurs between the target object and the own vehicle is predicted to obtain prediction result information.

For the description of S801 to S803, reference may be made to the above embodiments, which are not repeated herein.

S804: and determining a first relative distance between the target object and the vehicle according to the target positioning information and the vehicle positioning information.

The first relative distance may be a straight-line distance between the target object and the own vehicle when the prediction result information indicates that a collision event may occur between the target object and the own vehicle.

S805: and determining the relative speed between the target object and the vehicle according to the target speed vector and the vehicle speed vector.

The relative speed may be a speed difference value of the target object and the own vehicle in the first relative distance direction when the prediction result information indicates that a collision event may occur between the target object and the own vehicle.

S806: and determining a collision duration according to the first relative distance and the relative speed, wherein the collision duration is used as a first safety evaluation parameter.

Where the Time To Collision (TTC) is a Time length value calculated based on the first relative distance and the relative speed when the prediction result information indicates that a Collision event may occur between the target object and the own vehicle, and may be used To describe a Time difference between the current Time point and the Time point at which the Collision event is predicted To occur. The collision time depends on the first relative distance and the projection of the respective velocity vectors of the own vehicle and the target object in the direction of the first relative distance.

For example, the computational pseudo-code for TTC is as follows:

"time to collision = TTC (own vehicle positioning coordinate, target positioning coordinate, own vehicle velocity vector, target velocity vector)

{

Relative distance = the linear distance from the vehicle to the target;

relative speed = speed projection of the vehicle in the direction of the linear distance — speed projection of the target in the direction of the linear distance;

time-to-collision = relative distance/relative speed;

}”

inputting data:

location coordinates ([ x ]) of bicycle ₀ ,y ₀ ,z ₀ ]): and positioning coordinates of the own vehicle.

Target location coordinates ([ x ] _i ,y _i ,z _i ]): the location coordinates of the target object.

Target velocity vector (V) _i ＝[V _i,x ,V _i,y ,V _i,z ]): the magnitude and direction of the velocity of the target object.

Outputting data:

time To Collision (TTC): the time required for a collision to possibly occur in the current motion state.

For example, as shown in fig. 9, fig. 9 is a schematic diagram of a collision duration calculation according to an embodiment of the disclosure, wherein the speed v of the vehicle at point j is ₀ 3m/s, a linear distance of 3m from the predicted collision point k, a target object i at point l, and a velocity v _i 4m/s, the straight-line distance from the predicted collision point k is 4m, the first relative distance Δ X =5m of the two at this time, and the speed projection V of the corresponding speed vector of the own vehicle in the direction of the first relative distance _0⊥ 1.8m/s, the velocity projection V of the corresponding velocity vector of the target object in the first relative distance direction _i⊥ Is-3.2 m/s, the two areTime to collision t =5m/[1.8m/s- (-3.2 m/s)]＝1s。

The calculation formula of the velocity projection and the TTC may be as follows:

wherein, | | represents a vector modulo operation.

This problem translates into a general pursuit problem when the speed direction of the own vehicle and the target object coincides with the direction of the first relative distance, as shown in fig. 10, where fig. 10 is a schematic diagram illustrating calculation of the collision duration in a pursuit scene according to an embodiment of the present disclosure, where the own vehicle is located at a point m and the speed v is a ₀ =2m/s, the distance to the predicted collision point q is 8m, the target object i is located at point n, the velocity v is _i =1m/s, the distance from the predicted collision point q is 4m, the first relative distance Δ X =4m between the two, and the corresponding touch duration TTC =4 m/(2 m/s-1 m/s) =4s.

In this case, the velocity projection and TTC calculation formula is as follows:

optionally, in some embodiments, when generating the first safety evaluation parameter corresponding to the predicted occurrence of the collision event, the method may further include determining a relative acceleration between the target object and the vehicle according to the target acceleration vector and the vehicle acceleration vector, and determining an enhanced collision duration according to the first relative distance, the relative speed, and the relative acceleration, where the enhanced collision duration is used as the first safety evaluation parameter, so that the target acceleration vector and the vehicle acceleration vector may be effectively combined, the adaptability of the enhanced collision duration to the driving scene may be effectively improved, and the accuracy of the obtained first safety evaluation parameter may be effectively improved.

The relative acceleration is an acceleration difference between the target object and the own vehicle in the first relative distance direction when the prediction result information indicates that a collision event may occur between the target object and the own vehicle.

Where the Enhanced Time To Collision (ETTC) is a Time length value determined based on the first relative distance, the relative speed, and the relative acceleration when the prediction result information indicates that a Collision event may occur between the target object and the own vehicle, and may be used To describe a Time difference between the current Time point and the Time point at which the Collision event is predicted To occur.

The calculation pseudocode for ETTC is as follows:

"enhanced time to collision = ETTC (own vehicle positioning coordinate, target positioning coordinate, own vehicle velocity vector, target velocity vector, own vehicle acceleration vector, target acceleration vector)

{

Relative distance = the straight-line distance between the vehicle and the target;

relative acceleration = acceleration projection of the vehicle in the direction of the linear distance-acceleration projection of the target in the direction of the linear distance;

}”

inputting data:

coordinates ([ x ]) of bicycle ₀ ,y ₀ ,z ₀ ]): and positioning coordinates of the self vehicle.

Target coordinate ([ x ] _i ,y _i ,z _i ]): the location coordinates of the object.

Target velocity vector (V) _i ＝[V _i,x ,V _i,y ,V _i,z ]): the speed and direction of the target.

Acceleration vector (a) of bicycle ₀ ＝[a _0,x ,a _0,y ,a _0,z ]): the acceleration and direction of the vehicle.

Target acceleration vector (a) _i ＝[a _i,x ,a _i,y ,a _i,z ]): magnitude and direction of acceleration of the target.

Outputting data:

enhanced Time To Collision (ETTC): the time required for a collision to possibly occur in the current motion state.

For example, the ETTC may be calculated in a manner similar to the TTC by projecting a speed and an acceleration in a first relative distance direction between the host vehicle and the target object, and projecting a speed V between the host vehicle and the target object i _0⊥ And V _i⊥ Acceleration projection a _0⊥ And a _i⊥ And the ETTC calculation can be as follows:

wherein Δ a ≠ t = a _ (i ≠ a |) -a _ (0 |) is the relative acceleration in the first relative distance direction.

It will be appreciated that the enhanced crash time period (ETTC) may be selected for calculation in the general case, and the crash time period (TTC) may be selected for calculation when the acceleration is small (less than 1% of the current vehicle speed), or when acceleration data is not available. By utilizing the ETTC, the problem that the TTC is calculated inaccurately under the condition that the vehicle and the target object have acceleration is effectively solved.

And the calculation of the TTC or the ETTC can measure the threat degree of surrounding traffic participants or obstacles to the normal running of the vehicle and quantify the reaction time of the vehicle in the simulation or actual running process. The smaller the TTC/ETTC, the more dangerous the environment and the shorter the time to collision. For a set of automatic driving algorithm, the smaller the minimum TTC/ETTC with each target around, the safer the condition of the automatic driving automobile is; the smaller the global average minimum TTC/ETTC, the better the autodrive algorithm's performance in preventing hazards.

Optionally, in some embodiments, when generating the first safety evaluation parameter corresponding to the predicted occurrence of the collision event, the first safety evaluation parameter may further be determined according to the collision duration or the enhanced collision duration, the predicted collision point position information may be determined according to the self-vehicle positioning information and the predicted collision point position information, the second relative distance between the self-vehicle and the predicted collision point may be determined according to the self-vehicle velocity vector and the second relative distance, and the collision avoidance deceleration may be determined according to the self-vehicle velocity vector and the second relative distance, where the collision avoidance deceleration is used as the first safety evaluation parameter, and thus, the obtained first safety evaluation parameter may accurately indicate the avoidance of the collision event and the magnitude of the acceleration required to be taken during the deceleration process of the self-vehicle, so as to determine whether the collision event can be avoided, so that when the maximum braking acceleration of the self-vehicle cannot meet the collision avoidance deceleration, other deceleration measures may be taken in time, and the safety during driving may be improved to a greater extent.

The collision point position refers to a position where a collision event may occur between the own vehicle and the target object.

The second relative distance may be a distance between the location of the vehicle and the location of the expected collision point.

The Collision avoidance Deceleration (DRAC) may be an acceleration required during Deceleration of the own vehicle in order to Avoid a Collision event with the target object.

The computational pseudocode for a DRAC is as follows:

"collision reduction = DRAC (vehicle location coordinates, coordinates of expected collision point, vehicle velocity vector)

{

Relative distance = distance from the vehicle to the expected collision point;

}”

inputting data:

location coordinates of the vehicle ([ x ] ₀ ,y ₀ ,z ₀ ]): and positioning coordinates of the self vehicle.

Predicted collision point coordinates ([ x ]) _i ,y _i ,z _i ]): and the positioning coordinates of the predicted collision point are calculated according to the TTC and the speed vector of the vehicle, or the positioning coordinates of the predicted collision point are calculated according to the ETTC, the speed vector of the vehicle and the acceleration vector.

Outputting data:

For example, in calculating the location of the collision point (x) _t ,y _t ,z _t ) When, it may be the use of the length of the collision (i.e. t = TTC):

[x _t ,y _t ,z _t ]＝x ₀ +V _0,x t,y ₀ +V _0,y t,z ₀ +V _0,z t]；

alternatively, it is also possible to use an enhanced collision duration (i.e. t = ETTC):

thus, the calculation formula of the collision deceleration can be expressed as:

it can be understood that the calculation of the DRAC can measure the urgency of collision occurrence and can be used for judging whether the current collision risk can be normally avoided. The larger the collision avoidance deceleration is, the more urgent the collision is; if the collision avoidance deceleration exceeds the maximum braking acceleration of the self-vehicle, emergency danger avoidance needs to be carried out in other modes; in the whole driving process, the smaller the average DRAC is, the emergency braking frequency can be effectively reduced, and the collision avoidance performance of the automatic driving algorithm is improved.

That is, in the embodiment of the present disclosure, when the prediction result information indicates that a collision event may occur between the target object and the own vehicle, a first relative distance between the target object and the own vehicle may be determined according to the target positioning information and the own vehicle positioning information, a relative speed between the target object and the own vehicle may be determined according to the target speed vector and the own vehicle speed vector, and a collision duration may be determined according to the first relative distance and the relative speed, where the collision duration is used as a first safety evaluation parameter, and thus, the obtained first safety evaluation parameter may accurately represent a duration from a current time point when the collision event occurs, so as to be used for taking a corresponding emergency measure according to the collision duration.

S807: collision region position information between the target object and the own vehicle is determined.

The conflict area may be an overlapping area of the target object and the corresponding motion trail of the own vehicle. And the position information of the conflict area can be used for describing the relevant information of the conflict area, such as the shape, the area, the size and the like.

S808: and determining a first time length required for the self vehicle to enter the collision area and a second time length required for the self vehicle to leave the collision area according to the self vehicle positioning information, the collision area position information, the self vehicle speed vector and the self vehicle acceleration vector.

The first time length is the time length required for the vehicle to enter the collision area. The second time duration is the time duration required for the vehicle to leave the collision area.

For example, the distance from the vehicle position to the collision point position is d ₀ The collision area may be a circular area with a collision point as a center and a radius of R, and the driving distance of the vehicle is d when the first time duration is calculated ₀ -R, the distance travelled by the host vehicle when calculating the second time duration, is d ₀ +R。

S809: and determining a third time length required by the target object to enter the conflict area and a fourth time length required by the target object to leave the conflict area according to the target positioning information, the conflict area position information, the target speed vector and the target acceleration vector.

The third time length is the time length required for the target object to enter the conflict area. The fourth time duration is the time duration required for the target object to leave the collision area.

For example, the distance from the vehicle position to the collision point position is d ₁ The collision area may be a circular area with the collision point as a center and the radius of R, and the travel distance of the vehicle is d when the third time length is calculated ₁ -R, the distance traveled by the host vehicle is d when calculating the fourth time duration ₁ +R。

S810: and determining the post-encroachment time according to the first time length, the second time length, the third time length and the fourth time length, wherein the post-encroachment time is used as a second safety evaluation parameter.

The Post-invasion time (PET) is a time difference between the host vehicle and the target object occupying the collision area when the prediction result information indicates that the collision event does not occur between the target object and the host vehicle.

The PET calculation pseudocode is as follows:

"late encroachment time = PET (host vehicle positioning coordinate, target positioning coordinate, path intersection coordinate, host vehicle velocity vector, target velocity vector, host vehicle acceleration vector, target acceleration vector, radius of conflict region R)

{

d1= distance between the own vehicle and the path intersection;

d2= distance between target object and path intersection;

calculating the time t1 required by the vehicle to enter a collision area (travel distance d 1-R);

calculating the time t2 required by the vehicle to leave the collision region (the running distance d1+ R);

calculating the time t3 required by the target object to enter a collision area (driving distance d 2-R);

calculating the time t4 required by the target object to drive away from the collision region (the driving distance d2+ R);

if (t 2< t 3) \ \ own vehicle drives away from the conflict area first, and the target object enters the conflict area again

PET＝t3–t2；

else if (t 1< t 4) \ \ target object drives away from the conflict area first, and then the own vehicle enters the conflict area

PET＝t4–t1；

The case where else PET =0\, exists in the conflict region at the same time

}”

For example, as shown in fig. 11, fig. 11 is a schematic diagram of acquiring a late encroachment time according to an embodiment of the disclosure, and taking an example that a vehicle enters a collision area first, PET = t ₃ -t ₂ I.e. late encroachment time = third duration-second duration, i.e. target object 1 (speed v) ₁ ) Go intoTime to collision zone to own vehicle (speed v) ₀ ) And (3) selecting a circular area with a path intersection point as the center and a radius length of R (specific data can be flexibly configured according to an application scene) from the conflict area according to the time difference of the time when the conflict area leaves. It is to be understood that, in the application scenario, it may also be that the target object enters the collision area first, and then the late encroachment time = the first time length — the fourth time length.

If the late-encroachment time is 0, it is described that although the distance between the vehicle and the target object is not smaller than the collision risk threshold, the vehicle and the target object may be present in the collision area at the same time, and certain potential safety hazards exist. This occurs because the radius of the conflict area is chosen to be equal to the collision risk threshold because of the inconsistency between the radius of the conflict area and the collision risk determination threshold.

And the calculation of the post-encroachment time can represent the distance risk between the vehicle and the target object. The smaller the late-encroachment time is, the closer the distance between the vehicle and the target object is when the vehicle passes through the track junction, and the larger the risk is. The evaluation parameter can linearly evaluate safety and can be well used as a safety evaluation standard among automatic driving algorithms.

That is, the embodiment of the present disclosure may determine collision region position information between the target object and the own vehicle when the prediction result information indicates that a collision event does not occur between the target object and the own vehicle, determine a first time period required for the own vehicle to enter the collision region and a second time period required for the own vehicle to leave the collision region according to the own vehicle positioning information, the collision region position information, the own vehicle speed vector, and the own vehicle acceleration vector, determine a third time period required for the target object to enter the collision region and a fourth time period required for the own vehicle to leave the collision region according to the target positioning information, the collision region position information, the target speed vector, and the target acceleration vector, and determine a post-intrusion time period according to the first time period, the second time period, the third time period, and the fourth time period, wherein the post-intrusion time period is used as a second security evaluation parameter, and thus the obtained second security evaluation parameter may accurately represent a time difference in which the own vehicle and the target object occupy the collision region in the driving scene, and may be linearly evaluated based on the second security evaluation parameter, and clarity of the obtained second security evaluation parameter may be effectively improved.

For example, as shown in fig. 12, fig. 12 is a schematic diagram illustrating a security evaluation parameter acquiring process according to an embodiment of the disclosure, and in a driving scene, the following steps may be taken to acquire the security evaluation parameter:

1. acquiring relevant information (such as positioning information, a speed vector, an acceleration vector and the like) of the vehicle and the candidate object by a sensing system which is configured in the vehicle in advance;

2. calculating candidate risk values (i.e. speed distance alarms SDC) of a plurality of candidate objects and ranking the plurality of candidate objects based on SDC;

3. judging whether the candidate object is processed;

4. when the candidate object is processed, ending the process;

5. when the candidate objects are not processed completely, sequentially predicting whether the candidate objects are likely to have collision events with the own vehicles;

6. when the candidate object and the own vehicle are predicted not to have a collision event, judging whether the candidate object and the own vehicle are crossed (namely, a collision area exists);

7. when the candidate object and the own vehicle do not have the conflict area, executing the step 4;

8. when the candidate object and the vehicle have a conflict region, calculating the post-intrusion occupation time length PET of the candidate object and the vehicle as a second safety evaluation parameter, and executing the step 4;

9. when the candidate object and the own vehicle are predicted to possibly have a collision event, whether a preset condition is met or not is judged, wherein the preset condition can be as follows: whether the sensing system can acquire the acceleration of the sensing system and the vehicle speed are larger than a preset threshold value;

10. when a preset condition is met, an enhanced collision duration ETTC can be calculated as a first safety evaluation parameter;

11. when the preset condition is not met, calculating a collision duration TTC as a first safety evaluation parameter;

12. using the ETTC or TTC obtained in step 10 or step 11, a Collision avoidance Deceleration (DRAC) is calculated, and the above-mentioned step 4 is performed.

In the embodiment, a first relative distance between a target object and a vehicle of the vehicle is determined according to target positioning information and vehicle positioning information, a relative speed between the target object and the vehicle of the vehicle is determined according to a target speed vector and a vehicle speed vector, and a collision duration is determined according to the first relative distance and the relative speed, wherein the collision duration is used as a first safety evaluation parameter, so that the obtained first safety evaluation parameter can accurately represent the duration of a collision event from a current time point, and is convenient for taking corresponding emergency measures according to the collision duration. The method comprises the steps of determining the relative acceleration between a target object and a vehicle according to a target acceleration vector and the vehicle acceleration vector, determining the enhanced collision duration according to a first relative distance, a relative speed and the relative acceleration, wherein the enhanced collision duration is used as a first safety evaluation parameter, and therefore the target acceleration vector and the vehicle acceleration vector can be effectively combined, the adaptability of the obtained enhanced collision duration to a driving scene can be effectively improved, and the accuracy of the obtained first safety evaluation parameter can be effectively improved. The method comprises the steps of determining predicted collision point position information according to collision duration or enhanced collision duration, determining a second relative distance between a vehicle and the predicted collision point according to vehicle positioning information and the predicted collision point position information, and determining collision avoidance deceleration according to a vehicle speed vector and the second relative distance, wherein the collision avoidance deceleration is used as a first safety evaluation parameter, so that the obtained first safety evaluation parameter can accurately indicate the acceleration required to be adopted in the deceleration process of the vehicle to avoid a collision event, and whether the collision event can be avoided is judged, so that when the maximum braking acceleration of the vehicle cannot meet the collision avoidance deceleration, other deceleration measures can be timely adopted, and the safety in the driving process can be greatly improved. The method comprises the steps of determining position information of a collision area between a target object and a vehicle, determining a first time length required for the vehicle to enter the collision area and a second time length required for the vehicle to leave the collision area according to the positioning information, the position information, the speed vector and the acceleration vector of the vehicle, determining a third time length required for the target object to enter the collision area and a fourth time length required for the target object to leave the collision area according to the positioning information, the position information, the speed vector and the acceleration vector of the vehicle, and determining a post-encroachment time according to the first time length, the second time length, the third time length and the fourth time length, wherein the post-encroachment time is used as a second safety evaluation parameter, so that the obtained second safety evaluation parameter can accurately represent the time difference of the vehicle and the target object occupying the collision area, the safety of the vehicle in a driving scene can be linearly evaluated based on the second safety evaluation parameter, and the description clearness of the obtained second safety evaluation parameter can be effectively improved.

Fig. 13 is a schematic structural diagram of a vehicle safety evaluation parameter determination device according to an embodiment of the present disclosure.

As shown in fig. 13, the vehicle safety evaluation parameter determination device 130 includes:

a first determining module 1301, configured to determine a candidate risk value corresponding to each candidate object, where the candidate risk value describes a risk situation that the candidate object introduces to the own vehicle;

a second determining module 1302, configured to determine a target object from the plurality of candidate objects according to the candidate risk values;

the processing module 1303 is used for predicting whether a collision event occurs between the target object and the own vehicle to obtain prediction result information;

and a survival module 1304 for generating a security evaluation parameter corresponding to the prediction result information.

In some embodiments of the present disclosure, as shown in fig. 14, fig. 14 is a schematic structural diagram of a safety evaluation parameter determination apparatus for a vehicle according to another embodiment of the present disclosure, where the first determination module 1301 includes:

a first determining sub-module 13011 for determining a candidate type of each candidate object;

the second determining sub-module 13012 is configured to determine a candidate risk value corresponding to each candidate object according to the candidate type.

In some embodiments of the present disclosure, the second determining submodule 13012 is specifically configured to:

acquiring a risk weight factor corresponding to the candidate type;

acquiring candidate positioning information and a candidate speed vector of a candidate object, and acquiring self-vehicle positioning information and a self-vehicle speed vector of a self-vehicle;

and processing the candidate positioning information, the candidate speed vector, the self-vehicle positioning information and the self-vehicle speed vector according to the risk weight factor to obtain a candidate risk value.

In some embodiments of the present disclosure, the second determining submodule 13012 is further configured to:

determining a first risk factor introduced by a lateral distance between the candidate object and the own vehicle according to the candidate positioning information and the own vehicle positioning information;

determining a second risk factor introduced by a relative speed between the candidate object and the own vehicle, based on the candidate speed vector and the own vehicle speed vector;

the first risk factor and the second risk factor are processed according to the risk weight factor to obtain a candidate risk value.

In some embodiments of the present disclosure, the second determining module 1302 is specifically configured to:

and selecting a candidate object corresponding to the candidate risk value larger than the risk threshold value from the plurality of candidate objects as a target object.

In some embodiments of the present disclosure, the processing module 1303 is specifically configured to:

acquiring target positioning information, a target speed vector and a target acceleration vector of a target object;

acquiring the self-vehicle positioning information, the self-vehicle speed vector and the self-vehicle acceleration vector of a self-vehicle;

determining a plurality of target position points respectively corresponding to the plurality of predicted time points according to the target positioning information, the target velocity vector and the target acceleration vector;

determining a plurality of vehicle position points respectively corresponding to the plurality of predicted time points according to the vehicle positioning information, the vehicle speed vector and the vehicle acceleration vector;

determining a plurality of distance values corresponding to the plurality of predicted time points respectively, wherein the distance values describe distances between the target position point and the vehicle position point at the corresponding predicted time points;

and determining the prediction result information according to the plurality of distance values.

In some embodiments of the present disclosure, the processing module 1303 is further configured to:

when the distance value corresponding to at least one prediction time point is smaller than or equal to the distance threshold value, determining that the prediction result information is predicted to generate a collision event;

and when the distance value corresponding to any prediction time point is larger than the distance threshold value, determining that the prediction result information is that no collision event is predicted.

In some embodiments of the present disclosure, the generating module 1304 includes:

a first generation submodule 13041 for generating a first safety evaluation parameter corresponding to the predicted occurrence of the collision event; or

And a second generation submodule 13042 for generating a second safety evaluation parameter corresponding to the predicted non-occurrence of the collision event.

In some embodiments of the present disclosure, the first generation submodule 13041 is specifically configured to:

determining a first relative distance between the target object and the vehicle of the vehicle according to the target positioning information and the vehicle positioning information;

determining a relative speed between the target object and the vehicle of the vehicle according to the target speed vector and the vehicle speed vector;

determining a collision duration according to the first relative distance and the relative speed, wherein the collision duration is used as a first safety evaluation parameter.

In some embodiments of the present disclosure, the first generating submodule 13041 is further configured to:

determining the relative acceleration between the target object and the vehicle according to the target acceleration vector and the vehicle acceleration vector;

and determining an enhanced collision duration according to the first relative distance, the relative speed and the relative acceleration, wherein the enhanced collision duration is used as a first safety evaluation parameter.

In some embodiments of the present disclosure, the first generation submodule 13041 is further configured to:

determining the position information of the predicted collision point according to the collision duration or the enhanced collision duration;

determining a second relative distance between the self-vehicle and the predicted collision point according to the self-vehicle positioning information and the predicted collision point position information;

and determining the collision avoidance deceleration according to the vehicle speed vector and the second relative distance, wherein the collision avoidance deceleration is used as a first safety evaluation parameter.

In some embodiments of the present disclosure, the second generation submodule 13042 is specifically configured to:

determining collision region position information between the target object and the own vehicle;

determining a first time length required for the self vehicle to enter the collision area and a second time length required for the self vehicle to leave the collision area according to the self vehicle positioning information, the collision area position information, the self vehicle speed vector and the self vehicle acceleration vector;

determining a third time length required by the target object to enter the conflict area and a fourth time length required by the target object to leave the conflict area according to the target positioning information, the conflict area position information, the target speed vector and the target acceleration vector;

and determining the late encroachment time according to the first time length, the second time length, the third time length and the fourth time length, wherein the late encroachment time is used as a second safety evaluation parameter.

It should be noted that the above explanation of the method for determining the safety evaluation parameter of the vehicle is also applicable to the device for determining the safety evaluation parameter of the vehicle of the present embodiment, and is not repeated here.

In the embodiment, the candidate risk value corresponding to each candidate object is determined, wherein the candidate risk value describes a risk condition introduced by the candidate object to the own vehicle, the target object is determined from the candidate objects according to the candidate risk value, whether a collision event occurs between the target object and the own vehicle is predicted, so that prediction result information is obtained, the safety evaluation parameter corresponding to the prediction result information is generated, the safety state of each candidate object can be quantified based on the candidate risk value, the safety evaluation process is more pertinent, and more accurate safety evaluation parameters can be obtained.

Fig. 15 is a schematic structural diagram of a vehicle according to an embodiment of the present disclosure.

As shown in fig. 15, the vehicle 150 includes:

a processor 1501; a memory 1502 for storing processor 1501 executable instructions; wherein the processor 1501 is configured to: the method for determining the safety evaluation parameters of the vehicle is achieved.

Corresponding to the method for determining the safety evaluation parameter of the vehicle provided in the embodiment of fig. 1 to 12, the present disclosure also provides a vehicle, and since the vehicle provided in the embodiment of the present disclosure corresponds to the method for determining the safety evaluation parameter of the vehicle provided in the embodiment of fig. 1 to 12, the embodiment of the method for determining the safety evaluation parameter of the vehicle is also applicable to the vehicle provided in the embodiment of the present disclosure, and will not be described in detail in the embodiment of the present disclosure.

FIG. 16 illustrates a block diagram of an exemplary electronic device suitable for use in implementing embodiments of the present disclosure. The electronic device 12 shown in fig. 16 is only an example and should not bring any limitation to the function and the scope of use of the embodiments of the present disclosure.

As shown in fig. 16, the electronic device 12 is in the form of a general purpose computing device. The components of electronic device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including the system memory 28 and the processing unit 16.

Bus 18 represents one or more of any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, and a processor or local bus using any of a variety of bus architectures. These architectures include, but are not limited to, industry Standard Architecture (ISA) bus, micro Channel Architecture (MAC) bus, enhanced ISA bus, video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus, to name a few.

Electronic device 12 typically includes a variety of computer system readable media. Such media may be any available media that is accessible by electronic device 12 and includes both volatile and nonvolatile media, removable and non-removable media.

Memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM) 30 and/or cache memory 32. Electronic device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 16, and commonly referred to as a "hard drive").

Although not shown in FIG. 16, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a compact disk read Only memory (CD-ROM), a digital versatile disk read Only memory (DVD-ROM), or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the disclosure.

A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28, such program modules 42 including but not limited to an operating system, one or more application programs, other program modules, and program data, each of which or some combination of which may comprise an implementation of a network environment. Program modules 42 generally perform the functions and/or methodologies of the embodiments described in this disclosure.

Electronic device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), with one or more devices that enable a person to interact with electronic device 12, and/or with any devices (e.g., network card, modem, etc.) that enable electronic device 12 to communicate with one or more other computing devices. Such communication may be through an input/output (I/O) interface 22. Also, the electronic device 12 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public Network such as the Internet) via the Network adapter 20. As shown, the network adapter 20 communicates with the other modules of the electronic device 12 over the bus 18. It should be understood that although not shown in the figures, other hardware and/or software modules may be used in conjunction with electronic device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, to name a few.

The processing unit 16 executes various functional applications and data processing by running a program stored in the system memory 28, for example, implementing the vehicle safety evaluation parameter determination method mentioned in the foregoing embodiment.

In order to achieve the above embodiments, the present disclosure also proposes a non-transitory computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method of determining a safety evaluation parameter of a vehicle as proposed in the foregoing embodiments of the present disclosure.

In order to achieve the above embodiments, the present disclosure also proposes a computer program product, which when executed by an instruction processor in the computer program product, executes a method for determining a safety evaluation parameter of a vehicle as proposed by the foregoing embodiments of the present disclosure.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

It will be understood that the present disclosure is not limited to the precise arrangements that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

It should be noted that, in the description of the present disclosure, the terms "first", "second", etc. are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. Further, in the description of the present disclosure, "a plurality" means two or more unless otherwise specified.

Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and the scope of the preferred embodiments of the present disclosure includes other implementations in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present disclosure.

It should be understood that portions of the present disclosure may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.

It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.

In addition, functional units in the embodiments of the present disclosure may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a separate product, may also be stored in a computer-readable storage medium.

The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc.

In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present disclosure. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

Although embodiments of the present disclosure have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present disclosure, and that changes, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present disclosure.

Claims

1. A method of determining a safety evaluation parameter of a vehicle, characterized by comprising:

determining a candidate risk value corresponding to each candidate object, wherein the candidate risk value describes a risk condition introduced by the candidate object to the own vehicle;

determining a target object from the plurality of candidate objects according to the candidate risk value;

predicting whether a collision event occurs between the target object and the own vehicle to obtain prediction result information;

and generating a safety evaluation parameter corresponding to the prediction result information.

2. The method of claim 1, wherein the determining the candidate risk value corresponding to each candidate object comprises:

determining a candidate type for each of the candidate objects;

and determining a candidate risk value corresponding to each candidate object according to the candidate type.

3. The method of claim 2, wherein said determining a candidate risk value corresponding to said each candidate object according to said candidate type comprises:

acquiring a risk weight factor corresponding to the candidate type;

acquiring candidate positioning information and a candidate speed vector of the candidate object, and acquiring self-vehicle positioning information and a self-vehicle speed vector of the self-vehicle;

and processing the candidate positioning information, the candidate speed vector, the self-vehicle positioning information and the self-vehicle speed vector according to the risk weight factor to obtain the candidate risk value.

4. The method of claim 3, wherein said processing said candidate position fix information, said candidate velocity vector, said own vehicle position fix information, and said own vehicle velocity vector according to said risk weight factor to obtain said candidate risk value comprises:

processing the first risk factor and the second risk factor according to the risk weight factor to obtain the candidate risk value.

5. The method of claim 1, wherein said determining a target object from a plurality of said candidate objects based on said candidate risk values comprises:

and selecting a candidate object corresponding to the candidate risk value larger than a risk threshold value from the candidate objects as the target object.

6. The method according to claim 1, wherein the predicting whether a collision event occurs between the target object and the own vehicle to obtain prediction result information includes:

acquiring target positioning information, a target speed vector and a target acceleration vector of the target object;

acquiring the self-vehicle positioning information, the self-vehicle speed vector and the self-vehicle acceleration vector of the self-vehicle;

determining a plurality of target position points respectively corresponding to a plurality of prediction time points according to the target positioning information, the target velocity vector and the target acceleration vector;

determining a plurality of self-vehicle position points respectively corresponding to the plurality of predicted time points according to the self-vehicle positioning information, the self-vehicle speed vector and the self-vehicle acceleration vector;

determining a plurality of distance values respectively corresponding to the plurality of predicted time points, wherein the distance values describe distances between the target position point and the vehicle position point at the corresponding predicted time points;

7. The method of claim 6, wherein said determining said prediction result information based on said plurality of distance values comprises:

if the distance value corresponding to at least one predicted time point is smaller than or equal to a distance threshold value, determining that the predicted result information is predicted to generate a collision event;

and if the distance value corresponding to any one of the prediction time points is larger than the distance threshold value, determining that the prediction result information is that no collision event is predicted.

8. The method of claim 7, wherein the generating security evaluation parameters corresponding to the prediction result information comprises:

generating a first safety evaluation parameter corresponding to the predicted collision event; or

Generating a second safety evaluation parameter corresponding to the predicted non-occurrence of a collision event.

9. The method of claim 8, wherein said generating a first safety rating parameter corresponding to said predicted crash event comprises:

determining a first relative distance between the target object and the own vehicle according to the target positioning information and the own vehicle positioning information;

determining a relative speed between the target object and the own vehicle according to the target speed vector and the own vehicle speed vector;

determining a collision duration according to the first relative distance and the relative speed, wherein the collision duration is used as the first safety evaluation parameter.

10. The method of claim 9, wherein said generating a first safety rating parameter corresponding to said predicted crash event further comprises:

determining the relative acceleration between the target object and the own vehicle according to the target acceleration vector and the own vehicle acceleration vector;

determining an enhanced collision duration according to the first relative distance, the relative speed and the relative acceleration, wherein the enhanced collision duration is used as the first safety evaluation parameter.

11. The method of claim 10, wherein said generating a first safety assessment parameter corresponding to said predicted crash event further comprises:

determining the position information of the expected collision point according to the collision duration or the enhanced collision duration;

determining a second relative distance between the vehicle and a predicted collision point according to the vehicle positioning information and the predicted collision point position information;

and determining collision-avoidance deceleration according to the vehicle speed vector and the second relative distance, wherein the collision-avoidance deceleration is used as the first safety evaluation parameter.

12. The method of claim 8, wherein said generating a second safety rating parameter corresponding to said predicted non-occurrence of a collision event comprises:

determining a first time length required for the self-vehicle to enter the collision area and a second time length required for the self-vehicle to leave the collision area according to the self-vehicle positioning information, the collision area position information, the self-vehicle speed vector and the self-vehicle acceleration vector;

and determining a late-encroachment time according to the first time length, the second time length, the third time length and the fourth time length, wherein the late-encroachment time is used as the second safety evaluation parameter.

13. A safety evaluation parameter determination device for a vehicle, characterized by comprising:

the first determination module is used for determining a candidate risk value corresponding to each candidate object, wherein the candidate risk value describes a risk condition introduced by the candidate object to the vehicle;

a second determining module, configured to determine a target object from the plurality of candidate objects according to the candidate risk value;

the processing module is used for predicting whether a collision event occurs between the target object and the own vehicle to obtain prediction result information;

and the survival module is used for generating a safety evaluation parameter corresponding to the prediction result information.

14. The apparatus of claim 13, wherein the first determining module comprises:

a first determining sub-module, configured to determine a candidate type of each candidate object;

and the second determining submodule is used for determining a candidate risk value corresponding to each candidate object according to the candidate type.

15. The apparatus of claim 14, wherein the second determination submodule is specifically configured to:

acquiring a risk weight factor corresponding to the candidate type;

16. The apparatus of claim 15, wherein the second determination submodule is further operable to:

determining a second risk factor introduced by a relative speed between the candidate object and the host vehicle, based on the candidate speed vector and the host vehicle speed vector;

17. The apparatus of claim 13, wherein the second determining module is specifically configured to:

18. The apparatus of claim 13, wherein the processing module is specifically configured to:

19. The apparatus of claim 18, wherein the processing module is further configured to:

when the distance value corresponding to at least one predicted time point is smaller than or equal to a distance threshold value, determining that the predicted result information is predicted to generate a collision event;

and when the distance value corresponding to any one of the prediction time points is larger than the distance threshold value, determining that the prediction result information is that no collision event is predicted.

20. The apparatus of claim 19, wherein the generating module comprises:

a first generation submodule for generating a first safety evaluation parameter corresponding to the predicted collision occurrence; or

And the second generation submodule is used for generating a second safety evaluation parameter corresponding to the predicted non-collision event.

21. The apparatus of claim 20, wherein the first generation submodule is specifically configured to:

22. The apparatus of claim 21, wherein the first generation submodule is further to:

determining a relative acceleration between the target object and the own vehicle according to the target acceleration vector and the own vehicle acceleration vector;

23. The apparatus of claim 22, wherein the first generation submodule is further to:

determining a second relative distance between the vehicle and the predicted collision point according to the vehicle positioning information and the predicted collision point position information;

24. The apparatus of claim 20, wherein the second generation submodule is specifically configured to:

determining a third time length required for the target object to enter the collision area and a fourth time length required for the target object to leave the collision area according to the target positioning information, the collision area position information, the target speed vector and the target acceleration vector;

25. A vehicle, characterized by comprising:

a processor; a memory for storing processor-executable instructions; wherein the processor is configured to: the steps of implementing the method for determining a safety evaluation parameter of a vehicle according to any one of claims 1 to 12.

26. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-12.